CtrlK
BlogDocsLog inGet started
Tessl Logo

koog-assistant

Concise general-purpose assistant powered by JetBrains Koog. Use when a brief, focused answer is preferable to long-form output.

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/koog-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is appropriately concise and provides a clear, actionable word-limit rule for a simple skill. It earns high marks for token efficiency and workflow clarity, with only minor room for slightly more explicit guidance coverage and organization.

DimensionReasoningScore

Conciseness

The two-sentence body is lean and assumes Claude's competence with no padding or pre-explained concepts, matching 'lean and efficient; assumes Claude's competence; every token earns its place'.

5 / 5

Actionability

'Keep responses under 500 words unless asked for more detail' is a concrete, executable rule, fitting 'mostly executable guidance; concrete code or commands with minor gaps'; it is not 5 because coverage of common cases beyond the word limit is absent, and not 3 because the guidance is real and specific rather than pseudocode-level.

4 / 5

Workflow Clarity

This is a simple single-purpose skill whose single action (keep responses under 500 words) is unambiguous, so the simple-skill exception applies and workflow clarity scores 5; no validation checkpoints are required because no destructive or batch operations exist.

5 / 5

Progressive Disclosure

The body is under 50 lines with no external references needed, so the simple-skill exception applies; it is appropriately minimal with no monolithic wall or nested references, but lacks any section headers, leaving a minor organization gap that keeps it at 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

38%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is grammatically clean and includes an explicit Use-when clause, but its 'general-purpose assistant' framing is vague and non-distinctive, leaving it hard to differentiate from other skills. Concrete capabilities and natural trigger terms are largely absent.

Suggestions

Replace 'general-purpose assistant' with 1-3 concrete capabilities this skill actually performs so the 'what' is specific.

Add natural user-facing trigger terms (e.g., phrases or keywords a user would actually say) to the Use-when clause instead of abstract phrasing like 'long-form output'.

Narrow the scope or add a distinct niche tied to JetBrains Koog so it does not conflict with general assistant skills.

DimensionReasoningScore

Specificity

The description names the domain ('Concise general-purpose assistant powered by JetBrains Koog') but offers no concrete actions beyond 'assistant', matching the 'names the domain but actions are minimal or generic' anchor; it is not score 1 because a domain is named, and not 3 because no concrete capability is enumerated.

2 / 5

Completeness

Both a 'what' (concise assistant) and an explicit 'Use when...' clause are present, matching 'has both what and when; when could be more explicit or specific'; it is not 5 because the 'when' lacks concrete trigger phrases, and not 3 because the Use-when clause is explicit rather than missing.

4 / 5

Trigger Term Quality

Trigger phrases 'brief, focused answer is preferable to long-form output' are generic and unlikely to be the exact words a user utters when needing this skill, fitting 'one or two generic keywords; missing the natural phrases users say'; it does not reach 3 because no commonly varied synonyms are present.

2 / 5

Distinctiveness Conflict Risk

'general-purpose assistant' is entirely generic and would overlap with virtually any other skill, matching the score-1 anchor; the JetBrains Koog tie-in is the only distinguishing element but does not by itself carve a distinct niche.

1 / 5

Total

9

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Atmosphere/atmosphere
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.